0. Import libraries and load data¶
In [1]:
from sklearn.datasets import load_files
from keras.utils import np_utils
import numpy as np
from glob import glob
In [2]:
# define function to load train, test, and validation datasets
def load_dataset(path):
data = load_files(path)
paths = np.array(data['filenames'])
targets = np_utils.to_categorical(np.array(data['target']))
return paths, targets
In [3]:
all_files, all_targets = load_dataset('../data/all_images')
In [4]:
print('There are a total of %d labeled images in your dataset.' % len(all_files))
1. Image preprocessing¶
In [5]:
# Visualize what the data looks like
import cv2
import matplotlib.pyplot as plt
%matplotlib inline
def visualize_img(img_path, ax):
img = cv2.imread(img_path)
ax.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
fig = plt.figure(figsize=(180 ,160))
for i in range(36):
ax = fig.add_subplot(6, 6, i + 1, xticks=[], yticks=[])
visualize_img(all_files[i], ax)
